Progressive Estimation
Estimate AI-assisted and hybrid human+agent development work using research-backed formulas with PERT statistics, confidence bands, and calibration feedback loops.
Overview
Progressive Estimation adapts to your team's working mode — human-only, hybrid, or agent-first — applying the right velocity model and multipliers for each. It produces statistical estimates rather than gut feelings.
When to Use This Skill
- Estimating development tasks where AI agents handle part of the work
- Sprint planning with hybrid human+agent teams
- Batch sizing a backlog (handles 5 or 500 issues)
- Staffing and capacity planning with agent multipliers
- Release date forecasting with confidence intervals
How It Works
- Mode Detection — Determines if the team works human-only, hybrid, or agent-first
- Task Classification — Categorizes by size (XS–XL), complexity, and risk
- Formula Application — Applies research-backed multipliers grounded in empirical studies
- PERT Calculation — Produces expected values using three-point estimation
- Confidence Bands — Generates P50, P75, P90 intervals
- Output Formatting — Formats for Linear, JIRA, ClickUp, GitHub Issues, Monday, or GitLab
- Calibration — Feeds back actuals to improve future estimates
Examples
Single task:
"Estimate building a REST API with authentication using Claude Code"
Batch mode:
"Estimate these 12 JIRA tickets for our next sprint"
With context:
"We have 3 developers using AI agents for ~60% of implementation. Estimate this feature."
Best Practices
- Start with a single task to calibrate before moving to batch mode
- Feed back actual completion times to improve the calibration system
- Use "instant mode" for quick T-shirt sizing without full PERT analysis
- Be explicit about team composition and agent usage percentage
Common Pitfalls
Problem: Overconfident estimates
Solution: Use P75 or P90 for commitments, not P50
Problem: Missing context
Solution: The skill asks clarifying questions — provide team size and agent usage
Problem: Stale calibration
Solution: Re-calibrate when team composition or tooling changes significantly
Related Skills
@sprint-planning - Sprint planning and backlog management@project-management - General project management workflows@capacity-planning - Team velocity and capacity planning
Additional Resources
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
1---2name: progressive-estimation3description: Estimate AI-assisted and hybrid human+agent development work with research-backed PERT statistics and calibration feedback loops4license: MIT5---6
7# Progressive Estimation
8
9Estimate AI-assisted and hybrid human+agent development work using research-backed formulas with PERT statistics, confidence bands, and calibration feedback loops.
10
11## Overview
12
13Progressive Estimation adapts to your team's working mode — human-only, hybrid, or agent-first — applying the right velocity model and multipliers for each. It produces statistical estimates rather than gut feelings.
14
15## When to Use This Skill
16
17- Estimating development tasks where AI agents handle part of the work
18- Sprint planning with hybrid human+agent teams
19- Batch sizing a backlog (handles 5 or 500 issues)
20- Staffing and capacity planning with agent multipliers
21- Release date forecasting with confidence intervals
22
23## How It Works
24
251. **Mode Detection** — Determines if the team works human-only, hybrid, or agent-first
262. **Task Classification** — Categorizes by size (XS–XL), complexity, and risk
273. **Formula Application** — Applies research-backed multipliers grounded in empirical studies
284. **PERT Calculation** — Produces expected values using three-point estimation
295. **Confidence Bands** — Generates P50, P75, P90 intervals
306. **Output Formatting** — Formats for Linear, JIRA, ClickUp, GitHub Issues, Monday, or GitLab
317. **Calibration** — Feeds back actuals to improve future estimates
32
33## Examples
34
35**Single task:**
36> "Estimate building a REST API with authentication using Claude Code"
37
38**Batch mode:**
39> "Estimate these 12 JIRA tickets for our next sprint"
40
41**With context:**
42> "We have 3 developers using AI agents for ~60% of implementation. Estimate this feature."
43
44## Best Practices
45
46- Start with a single task to calibrate before moving to batch mode
47- Feed back actual completion times to improve the calibration system
48- Use "instant mode" for quick T-shirt sizing without full PERT analysis
49- Be explicit about team composition and agent usage percentage
50
51## Common Pitfalls
52
53- **Problem:** Overconfident estimates
54 **Solution:** Use P75 or P90 for commitments, not P50
55
56- **Problem:** Missing context
57 **Solution:** The skill asks clarifying questions — provide team size and agent usage
58
59- **Problem:** Stale calibration
60 **Solution:** Re-calibrate when team composition or tooling changes significantly
61
62## Related Skills
63
64- `@sprint-planning` - Sprint planning and backlog management
65- `@project-management` - General project management workflows
66- `@capacity-planning` - Team velocity and capacity planning
67
68## Additional Resources
69
70- [Source Repository](https://github.com/Enreign/progressive-estimation)
71- [Installation Guide](https://github.com/Enreign/progressive-estimation/blob/main/INSTALLATION.md)
72- [Research References](https://github.com/Enreign/progressive-estimation/tree/main/references)
73
74## Limitations
75- Use this skill only when the task clearly matches the scope described above.
76- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
77- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
nous-hermeshub